Nada Adnan Taher

Background: The length and depth of global supply networks have been rising over time, causing permanent problems in visibility, protection, and performance. Blockchain technology has come out as a disruptive technology to tackle all these problems, by providing decentralized, safe and transparent systems.  Objective: This article examines the use of blockchain technology within the context of supply chain and specifically digs deeper into the area of increased transparency, security and subsequent efficient supply chain transactions. The aim is to show that it is possible to transform resource supply chain operations through blockchain and engender trust amongst stakeholders. Methods: Permissioned blockchain system has been design and implemented using proof of Authority (PoA) consensus algorithm. IoT sensors were deployed to obtain data in real-time, and smart contracts were incorporated to perform the tasks of product evaluation, and payment authorization. The performance of the system was assessed depending on the indicators including the number of transactions per time or volume per time, time taken for each transaction, auditability and workability. Results: The combination of high transaction throughput with low latency made the blockchain system scalable as well as operationally stable. Smart contracts were able to minimize the time taken and mistakes, and improve the integration of IoT in relation to tracing transactions in real time. The system also proved that it had the ability to withstand cyber assaults and no data were compromised.  Conclusion: Based on the analysis of supply chain problems, blockchain technology can be used to transform supply chain management. Furthermore, more studies should be done on the future compatibility of the usage of such a system with new technology trends and also its implementation in multiple regions supply chain to harness this valuable system.

ABSTRACT Background: Artificial Intelligence (AI) has rapidly integrated into healthcare, proving indispensable in diagnostic processes. Event-predicting equations in medicine offer solutions to longstanding issues related to early diagnosis and personalized patient care. Objective: This article aims to explore best practices in objective and quantitative diagnostic predictions using AI and predictive algorithms. It seeks to revolutionize healthcare diagnostics by enhancing effectiveness and reducing diagnostic error rates. Methods: This study involves a literature review of the past five years, focusing on recent innovations in AI for healthcare diagnostics. The review includes fields such as oncology, cardiology, and others to evaluate the efficacy of prediction algorithms in practice. Results: The findings indicate that machine learning-based computer-aided diagnosis models significantly improve diagnostic accuracy by detecting diseases at early stages and personalizing treatment programs. The integration of these algorithms has led to reduced diagnostic errors and improved patient experiences across various medical fields. Conclusion: AI predictive algorithms represent the future of diagnostic medicine. Their adoption is set to personalize and advance patient treatment, enhance health outcomes, and improve the efficiency of healthcare systems. However, comprehensive research and precise implementation are essential to fully harness the potential of AI in diagnostics.